Search Tools MCP Server
Enables intelligent code analysis and search across repositories using the CodeRank algorithm (inspired by PageRank) to identify critical modules, trace dependencies, find code hotspots, and perform context-aware keyword searches with importance-ranked results.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
voxmenthe
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
analyze_recent_changesAnalyze recent changes using CodeRank to identify most important modifications. Aggregates changes over the last N days and ranks them by impact. Args: repo_path: Repository path (absolute) days_back: Number of days to look back for commits target_branch: Branch to analyze (default: main) min_commit…
get_commit_hotspotsFind modules that are frequently changed together in commits. Identifies coupled modules that might have hidden dependencies. Args: repo_path: Repository path days_back: Days to analyze min_cochange_frequency: Minimum times modules must change together top_n: Number of top coupled module pairs to re…
contributor_impact_analysisAnalyze contributor patterns and their impact on important modules. Identifies key contributors and their areas of expertise. Args: repo_path: Repository path days_back: Days to analyze min_commits: Minimum commits by a contributor to be included focus_on_important_modules: Weight contributions by m…
change_propagation_analysisAnalyze how changes in one module historically propagate to others. Uses commit history to predict ripple effects of changes. Args: repo_path: Repository path changed_module: Module to analyze (e.g., 'src.auth.user') days_back: Days of history to analyze include_test_impact: Include analysis of test…
contextual_keyword_searchSearch for a keyword in the current directory (wrapper around ripgrep).
get_repo_symbolsRun `kit symbols <repo>` and keep the header plus rows that satisfy the filters.
get_symbol_usagesRun `kit usages <repo> <symbol_name>` and optionally filter by symbol type at the CLI level and then post-filter the rows by file inclusion/exclusion substrings.
coderank_analysisAnalyze repository importance using CodeRank algorithm to identify critical modules. Args: repo_path: Path to the repository (absolute path) external_modules: Comma-separated list of external modules to track top_n: Number of top modules to return analyze_markdown: Include markdown files in analysis…
find_code_hotspotsIdentify code hotspots by combining CodeRank with symbol usage frequency. Uses kit usages + coderank to find modules that are both highly connected and frequently used. Args: repo_path: Repository to analyze working_directory: Working directory for commands (absolute path) min_connections: Minimum i…
trace_dependency_impactTrace dependency chains and analyze refactoring impact for a module. Combines dependency tracing with impact analysis. Args: repo_path: Repository path target_module: Module to analyze (e.g., 'src.auth.middleware') working_directory: Working directory (absolute path) analysis_type: "dependency" for …
smart_code_searchEnhanced search that combines ripgrep with CodeRank to prioritize results from more important modules. Args: keyword: Search term (supports regex) repo_path: Repository path working_directory: Working directory (absolute path) rank_results: Sort results by module importance context_lines: Lines of c…
trace_data_flowTrace how specific data flows through the system from source to destination. Use this tool when you need to understand: - How a piece of data (user_id, email, order_data, etc.) moves through the codebase - What functions transform or modify the data - Where data comes from and where it goes - What s…
analyze_error_patternsDiscover error handling patterns and inconsistencies in the codebase. Use this tool when you need to understand: - How errors are typically handled in this codebase - What error handling patterns to follow for consistency - Where error handling might be missing or inconsistent - How error handling h…
trace_feature_implementationMap all code involved in implementing a specific feature from UI to data layer. Use this tool when you need to: - Understand all components involved in a feature before modifying it - Map feature implementation across multiple layers (UI, business logic, data) - Find all related code that might be a…
find_api_usage_examplesFind real usage examples of APIs, functions, or classes in the codebase. Use this tool when you need to: - Learn how to properly use an existing API by seeing real examples - Understand the different ways an API is used across the codebase - Find patterns and best practices for API usage - See what …
discover_side_effectsDiscover all potential side effects of calling a function or method. Use this tool when you need to understand: - What else might happen when you call a specific function - All the systems/resources that might be affected by a function call - Potential unintended consequences of code changes - What …
map_integration_pointsMap all external integration points and their characteristics. Use this tool when you need to understand: - What external services or systems the codebase integrates with - How those integrations are implemented and configured - Error handling patterns for external dependencies - Potential failure p…
analyze_execution_pathsAnalyze all possible execution paths through a function and what triggers each path. Use this tool when you need to understand: - All the different ways a complex function can execute - What conditions or parameters lead to different code paths - Potential edge cases or error conditions - Decision p…
analyze_config_impactAnalyze what code is affected by specific configuration values. Use this tool when you need to understand: - What code will behave differently if you change a config setting - How configuration values flow through the system - What the default behavior is when config is missing - How configuration c…
identify_performance_bottlenecksIdentify potential performance bottlenecks by analyzing code patterns and complexity. Use this tool when you need to: - Find likely performance issues before they become problems - Prioritize optimization efforts on high-impact code - Understand which parts of the codebase might be slow - Plan perfo…
analyze_testing_strategyAnalyze testing strategies and identify gaps for better test coverage. Use this tool when you need to understand: - How different parts of the code are tested and what patterns are used - Where test coverage might be missing or insufficient - What testing frameworks and patterns the codebase follows…
OPENAI_API_KEYTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
25/25 tools missing one or more hints — analyze_recent_changes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_commit_hotspots (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); contributor_impact_analysis (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +22 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
9 tools describe read intent but their handlers mutate — analyze_recent_changes (line 78: log_result = subprocess.run(git_log_cmd, capture_output=True, text=True)); contextual_keyword_search (line 34: result = subprocess.run(); smart_code_search (line 775: rg_result = subprocess.run()
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool handlers catch errors
22/25 tool handlers wrap calls in try/catch (88%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
12 tools have description/behavior mismatches: analyze_recent_changes: description implies read-only but handler writes/deletes/executes; get_commit_hotspots: description implies read-only but handler writes/deletes/executes; contextual_keyword_search: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/voxmenthe/search-tools-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check